Non-uniform Speaker Disentanglement For Depression Detection From Raw Speech Signals
Authors:
- 20 August 2023
- conference paper
- Published by International Speech Communication Association in Interspeech
- Vol. 2023, 2343-2347
Abstract
While speech-based depression detection methods that use speaker-identity features, such as speaker embeddings, are popular, they often compromise patient privacy. To address this issue, we propose a speaker disentanglement method that utilizes a non-uniform mechanism of adversarial SID loss maximization. This is achieved by varying the adversarial weight between different layers of a model during training. We find that a greater adversarial weight for the initial layers leads to performance improvement. Our approach using the ECAPA-TDNN model achieves an F1-score of 0.7349 (a 3.7% improvement over audio-only SOTA) on the DAIC-WoZ dataset, while simultaneously reducing the speaker-identification accuracy by 50%. Our findings suggest that identifying depression through speech signals can be accomplished without placing undue reliance on a speaker’s identity, paving the way for privacy-preserving approaches of depression detection.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Unsupervised Instance Discriminative Learning for Depression Detection from Speech SignalsInterspeech, 2022
- A Step Towards Preserving Speakers’ Identity While Detecting Depression Via Speaker DisentanglementInterspeech, 2022
- Quantifying the separability of data classes in neural networksNeural Networks, 2021
- Using i-vectors from voice features to identify major depressive disorderJournal of Affective Disorders, 2021
- Digital privacy in mental healthcare: current issues and recommendations for technology useCurrent Opinion in Psychology, 2020
- Automatic Detection of Depression in Speech Using Ensemble Convolutional Neural NetworksEntropy, 2020
- Automated assessment of psychiatric disorders using speech: A systematic reviewLaryngoscope Investigative Otolaryngology, 2020
- Detecting Depression Severity from Vocal ProsodyIEEE Transactions on Affective Computing, 2012
- Speech characteristics as indicators of depressive illnessActa Psychiatrica Scandinavica, 1988
- Linguistic Analysis of Speech in Affective DisordersArchives of General Psychiatry, 1976